Audit log of write attempts

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioural context beyond that: the ordering contract (oldest first, returning the newest `limit` events) and the event-model detail that a call_id ties a live_intent to a live_result, live_error or live_unknown, which tells the agent what an indeterminate outcome looks like. It does not mention volume, truncation at the limit boundary, or empty-day behaviour, keeping it below 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences with no filler, and the identity of the resource is front-loaded. The parenthetical '(newest `limit`)' is slightly awkward and momentarily reads as if it contradicts 'oldest first', which costs it a point on clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry the return shape and it largely does, naming the event kinds and the correlation fields an agent needs to link an attempt to its outcome. For a three-parameter read-only log tool this is close to sufficient; only full field enumeration and result-volume behaviour are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with date, tool and limit all documented in the schema itself, so the baseline is 3. The description reinforces limit semantics ('oldest first (newest `limit`)') and hints at the tool filter through examples of event types, but adds no new syntax or format detail not already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (the audit log) and enumerates exactly what it contains: dry runs, refusals, confirmations, live sends and their results, plus the call_id correlation between live_intent and live_result/live_error/live_unknown. That is far more specific than the title alone. It does not, however, explicitly separate itself from lookalike siblings such as get_order_history or get_safety_status, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: by calling it 'the audit log' of write attempts an agent can infer this is the place to check what happened to a dry run or a refused/confirmed send. There is no explicit when-to-use statement, no mention of when another sibling (e.g. get_orders, get_order_history) is the better choice, and no prerequisites such as needing a session.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.